_utils/bubble_integrations/obter_arquivo.py

# from setup.easy_imports import PyPDFLoader
import os
from langchain_community.document_loaders import PyPDFLoader
import tempfile
import requests

from _utils.handle_files import return_document_list_with_llama_parser

headers = {"Authorization": f"Bearer {os.environ.get("BUBBLE_TOKEN")}"}


# def obter_arquivo(id_arquivo="1735864318176x375804955201372160"):
#     return requests.get(
#         f"https://vella.app.br/version-test/api/1.1/obj/formresponseanswer/{id_arquivo}",
#         headers=headers,
#     )


async def get_pdf_from_bubble(
    file_url=f"https://vella.app.br/version-test/fileupload/f1735864316650x718601440484441900/Boleto_DIGITICS%20Servic%CC%A7os%20de%20Secretariado%20LTDA_30_12_2024_804841714.pdf",
    should_use_llama_parse=False,
):
    if should_use_llama_parse:
        response = requests.get(file_url, headers=headers)
        response.raise_for_status()

        # Create a NamedTemporaryFile (with a .pdf suffix) to store the file
        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
            # Write the response content to the temporary file
            tmp_file.write(response.content)
            return await return_document_list_with_llama_parser(
                tmp_file.name
            )  # por enquanto este arquivo não está sendo excluído
    else:
        result = PyPDFLoader(file_url, headers=headers)

        return result.load()